How do I install the Code Review Trigger skill?

Run npx skillmds add majiayu000/code-review-trigger in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Code Review Trigger safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: docs only. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Code Review Trigger?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Code Review Trigger free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Code Review Trigger?

majiayu000 (@majiayu000) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Code Review Trigger by majiayu000 — Agent Skill

Name: Code Review Trigger
Rating: 4.2 (5 reviews)
Author: majiayu000

File contents

code-review-trigger

Type: ANALYSIS-ONLY DAIC Modes: DISCUSS, ALIGN, IMPLEMENT, CHECK (all modes) Priority: High

Trigger Reference

This skill activates on:

Keywords: "review code", "code review", "check for bugs", "validate code", "find issues", "analyze code", "check quality", "code quality", "review this", "check this code", "inspect code", "audit code", "review changes", "review file"
Intent Patterns: (review|check|validate|analyze).*?(code|file|changes|this), (find|detect|look for).*?(bug|issue|problem|error), code.*?quality, (inspect|audit).*?(code|file|changes)

From: skill-rules.json - code-review-trigger configuration

Purpose

Automatically trigger the /code-review slash command when users express intent to review code, check for bugs, or validate code quality using natural language. This skill eliminates the need to remember the exact /code-review syntax.

Core Behavior

In any DAIC mode:

Natural Language Detection
- Detect when user wants code review without using slash command
- Examples: "Review this code", "Check for bugs", "Is this code good?"
- Automatically invoke /code-review with appropriate arguments
Context Extraction
- Extract what should be reviewed from user's message
- Examples: "Review src/auth.js" → args: "src/auth.js"
- "Check for bugs in recent changes" → args: "recent changes"
- "Review this" (with file in context) → args: infer from context
Slash Command Invocation
- Call /code-review command with extracted arguments
- Pass through to multi-aspect parallel code review system
- Return results to user

Natural Language Examples

Triggers this skill:

✓ "Review this code"
✓ "Check for bugs in src/"
✓ "Validate code quality"
✓ "Find issues in my changes"
✓ "Analyze this file for problems"
✓ "Code review the recent commits"
✓ "Inspect the authentication logic"
✓ "Audit the API endpoints"

Does NOT trigger (too generic):

✗ "Code" (just mentions code)
✗ "Files" (no review intent)
✗ "What changed?" (status check, not review)

Safety Guardrails

ANALYSIS-ONLY RULES:

✓ NEVER call write tools (Edit, Write, MultiEdit)
✓ Only invokes /code-review command which is read-only
✓ Safe to run in any DAIC mode
✓ Provides analysis and suggestions only

Invocation Rules:

Only invoke /code-review when clear review intent detected
Extract specific targets from natural language when possible
Default to reviewing recent changes if no target specified
Never auto-fix issues (code-review is analysis-only)

Implementation Notes

This skill acts as a natural language wrapper around /code-review. The actual code review logic lives in .claude/commands/code-review.md, which:

Launches parallel code-review-expert agents
Analyzes code quality, security, performance, etc.
Returns comprehensive review findings

This skill simply detects the intent and routes to that command.

---name: code-review-triggerdescription: Natural language wrapper for code review - automatically triggers /code-review when users express intent to review code, check for bugs, or validate code quality--- # code-review-trigger **Type:** ANALYSIS-ONLY **DAIC Modes:** DISCUSS, ALIGN, IMPLEMENT, CHECK (all modes) **Priority:** High ## Trigger Reference This skill activates on: - **Keywords:** "review code", "code review", "check for bugs", "validate code", "find issues", "analyze code", "check quality", "code quality", "review this", "check this code", "inspect code", "audit code", "review changes", "review file" - **Intent Patterns:** `(review|check|validate|analyze).*?(code|file|changes|this)`, `(find|detect|look for).*?(bug|issue|problem|error)`, `code.*?quality`, `(inspect|audit).*?(code|file|changes)` From: `skill-rules.json` - code-review-trigger configuration ## Purpose Automatically trigger the `/code-review` slash command when users express intent to review code, check for bugs, or validate code quality using natural language. This skill eliminates the need to remember the exact `/code-review` syntax. ## Core Behavior In any DAIC mode: 1. **Natural Language Detection** - Detect when user wants code review without using slash command - Examples: "Review this code", "Check for bugs", "Is this code good?" - Automatically invoke `/code-review` with appropriate arguments 2. **Context Extraction** - Extract what should be reviewed from user's message - Examples: "Review src/auth.js" → args: "src/auth.js" - "Check for bugs in recent changes" → args: "recent changes" - "Review this" (with file in context) → args: infer from context 3. **Slash Command Invocation** - Call `/code-review` command with extracted arguments - Pass through to multi-aspect parallel code review system - Return results to user ## Natural Language Examples **Triggers this skill:** - ✓ "Review this code" - ✓ "Check for bugs in src/" - ✓ "Validate code quality" - ✓ "Find issues in my changes" - ✓ "Analyze this file for problems" - ✓ "Code review the recent commits" - ✓ "Inspect the authentication logic" - ✓ "Audit the API endpoints" **Does NOT trigger (too generic):** - ✗ "Code" (just mentions code) - ✗ "Files" (no review intent) - ✗ "What changed?" (status check, not review) ## Safety Guardrails **ANALYSIS-ONLY RULES:** - ✓ NEVER call write tools (Edit, Write, MultiEdit) - ✓ Only invokes /code-review command which is read-only - ✓ Safe to run in any DAIC mode - ✓ Provides analysis and suggestions only **Invocation Rules:** - Only invoke /code-review when clear review intent detected - Extract specific targets from natural language when possible - Default to reviewing recent changes if no target specified - Never auto-fix issues (code-review is analysis-only) ## Implementation Notes This skill acts as a natural language wrapper around `/code-review`. The actual code review logic lives in `.claude/commands/code-review.md`, which: - Launches parallel code-review-expert agents - Analyzes code quality, security, performance, etc. - Returns comprehensive review findings This skill simply detects the intent and routes to that command.

Frequently asked questions